Diffusion models have emerged as the leading paradigm in generative modeling, excelling
in various applications. Despite their success, these models often misalign with human …

Large language models are meticulously aligned to be both helpful and harmless. However,
recent research points to a potential overkill which means models may refuse to answer …

Most alignment research today focuses on designing new learning algorithms using
datasets like Anthropic-HH, assuming human feedback data is inherently reliable. However …

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from
extensive text corpora, making them powerful tools for various applications. To make LLMs …

The last decade in deep learning has brought on increasingly capable systems that are
deployed on a wide variety of applications. In natural language processing, the field has …

The ability of humans to estimate other's beliefs, mental states, and attitudes is referred to as
Theory of Mind (ToM)[3–8]. ToM is widely researched due to its alleged implications in …